9Router — Speech-to-Text
Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.
Discover
curl $NINEROUTER_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$NINEROUTER_URL/v1/models/info?id=openai/whisper-1"
model = STT model ID (e.g. openai/whisper-1, groq/whisper-large-v3, deepgram/nova-3, gemini/gemini-2.5-flash).
Endpoint
POST $NINEROUTER_URL/v1/audio/transcriptions (OpenAI Whisper compatible, multipart/form-data)
| Field |
Required |
Notes |
model |
yes |
from /v1/models/stt |
file |
yes |
audio file (mp3, wav, m4a, webm, ogg, flac) |
language |
no |
ISO-639-1 (e.g. en, vi) |
prompt |
no |
hint text to guide transcription |
response_format |
no |
json (default) / text / verbose_json / srt / vtt |
temperature |
no |
0–1 |
Examples
curl -X POST "$NINEROUTER_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $NINEROUTER_KEY" \
-F "model=openai/whisper-1" \
-F "file=@audio.mp3" \
-F "language=vi"
JS (Node):
import { createReadStream } from "node:fs";
const form = new FormData();
form.append("model", "groq/whisper-large-v3-turbo");
form.append("file", new Blob([await (await import("node:fs/promises")).readFile("audio.mp3")]), "audio.mp3");
const r = await fetch(`${process.env.NINEROUTER_URL}/v1/audio/transcriptions`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}` },
body: form,
});
const { text } = await r.json();
console.log(text);
Response shape
Default (response_format=json):
{ "text": "Xin chào, đây là bản ghi âm." }
verbose_json adds language, duration, segments[] with timestamps.
srt / vtt return subtitle text.
Provider quirks
| Provider |
model format |
Notes |
openai |
whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe |
Native OpenAI shape |
groq |
whisper-large-v3, whisper-large-v3-turbo, distil-whisper-large-v3-en |
Fastest; OpenAI shape |
gemini |
gemini-2.5-flash, gemini-2.5-pro, gemini-2.5-flash-lite |
Server converts to generateContent with audio inline |
deepgram |
nova-3, nova-2, whisper-large |
Token auth; server adapts response |
assemblyai |
universal-3-pro, universal-2 |
Async upload+poll handled server-side |
nvidia |
nvidia/parakeet-ctc-1.1b-asr |
NIM endpoint |
huggingface |
openai/whisper-large-v3, openai/whisper-small |
HF Inference API |
elevenlabs |
scribe_v1, scribe_v2 |
Whisper-compatible shape; xi-api-key auth, not Bearer. Extra params: timestamps_granularity (word/character/none), tag_audio_events, and speaker labelling via either diarize=true or num_speakers (1–32) — sending both makes the request invalid, so diarize wins and num_speakers is dropped. Blank language is omitted upstream for auto-detect. srt/vtt and verbose_json segments are served from Scribe's own additional_formats render, so segments[] is omitted when the upstream render is unavailable rather than synthesized. Does not accept temperature or prompt — those are not forwarded. |
1---2name: 9router-stt3description: Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.4metadata:5 source: https://skillmd.com/skills/tuyv/9router-stt6---78# 9Router — Speech-to-Text910Requires `NINEROUTER_URL` (and `NINEROUTER_KEY` if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.1112## Discover1314```bash15curl $NINEROUTER_URL/v1/models/stt | jq '.data[].id'16# Per-model params (language, response_format, prompt, temperature support)17curl "$NINEROUTER_URL/v1/models/info?id=openai/whisper-1"18```1920`model` = STT model ID (e.g. `openai/whisper-1`, `groq/whisper-large-v3`, `deepgram/nova-3`, `gemini/gemini-2.5-flash`).2122## Endpoint2324`POST $NINEROUTER_URL/v1/audio/transcriptions` (OpenAI Whisper compatible, `multipart/form-data`)2526| Field | Required | Notes |27|---|---|---|28| `model` | yes | from `/v1/models/stt` |29| `file` | yes | audio file (mp3, wav, m4a, webm, ogg, flac) |30| `language` | no | ISO-639-1 (e.g. `en`, `vi`) |31| `prompt` | no | hint text to guide transcription |32| `response_format` | no | `json` (default) / `text` / `verbose_json` / `srt` / `vtt` |33| `temperature` | no | 0–1 |3435## Examples3637```bash38curl -X POST "$NINEROUTER_URL/v1/audio/transcriptions" \39 -H "Authorization: Bearer $NINEROUTER_KEY" \40 -F "model=openai/whisper-1" \41 -F "file=@audio.mp3" \42 -F "language=vi"43```4445JS (Node):4647```js48import { createReadStream } from "node:fs";49const form = new FormData();50form.append("model", "groq/whisper-large-v3-turbo");51form.append("file", new Blob([await (await import("node:fs/promises")).readFile("audio.mp3")]), "audio.mp3");52const r = await fetch(`${process.env.NINEROUTER_URL}/v1/audio/transcriptions`, {53 method: "POST",54 headers: { "Authorization": `Bearer ${process.env.NINEROUTER_KEY}` },55 body: form,56});57const { text } = await r.json();58console.log(text);59```6061## Response shape6263Default (`response_format=json`):64```json65{ "text": "Xin chào, đây là bản ghi âm." }66```6768`verbose_json` adds `language`, `duration`, `segments[]` with timestamps.69`srt` / `vtt` return subtitle text.7071## Provider quirks7273| Provider | `model` format | Notes |74|---|---|---|75| `openai` | `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` | Native OpenAI shape |76| `groq` | `whisper-large-v3`, `whisper-large-v3-turbo`, `distil-whisper-large-v3-en` | Fastest; OpenAI shape |77| `gemini` | `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-2.5-flash-lite` | Server converts to `generateContent` with audio inline |78| `deepgram` | `nova-3`, `nova-2`, `whisper-large` | Token auth; server adapts response |79| `assemblyai` | `universal-3-pro`, `universal-2` | Async upload+poll handled server-side |80| `nvidia` | `nvidia/parakeet-ctc-1.1b-asr` | NIM endpoint |81| `huggingface` | `openai/whisper-large-v3`, `openai/whisper-small` | HF Inference API |82| `elevenlabs` | `scribe_v1`, `scribe_v2` | Whisper-compatible shape; `xi-api-key` auth, not Bearer. Extra params: `timestamps_granularity` (`word`/`character`/`none`), `tag_audio_events`, and speaker labelling via **either** `diarize=true` **or** `num_speakers` (1–32) — sending both makes the request invalid, so `diarize` wins and `num_speakers` is dropped. Blank `language` is omitted upstream for auto-detect. `srt`/`vtt` and `verbose_json` segments are served from Scribe's own `additional_formats` render, so `segments[]` is omitted when the upstream render is unavailable rather than synthesized. Does not accept `temperature` or `prompt` — those are not forwarded. |